A Patient-Specific Digital Twin for Adaptive Radiotherapy of Non-Small Cell Lung Cancer

2026-02-14

AI Summary

This study addresses the limitation of conventional radiotherapy, which relies on static population-based NTCP models that overlook dynamic biological changes in normal tissues during treatment for non-small cell lung cancer. The authors propose COMPASS—the first patient-specific digital twin system leveraging dense longitudinal data—integrating fractionated PET/CT imaging, dosiomics, radiomics, and cumulative biologically effective dose (BED) kinetics. A GRU autoencoder learns organ-specific latent trajectories, which are combined with logistic regression to predict CTCAE grade ≥1 toxicity. Evaluated on 99 organ observations from eight patients, the system successfully detected rising risk trends several fractions before toxicity onset, revealing an early warning window and biologically relevant spatial dose-texture features undetectable by conventional dosimetry. These findings demonstrate the feasibility of AI-driven adaptive radiotherapy.

Technology Category

• Cognitive Modeling & Cognitive Systems: Adaptive Behavior
• Machine Learning: Multimodal Learning
• Computer Vision: Multi-modal Vision

Application Category

• User Modeling, Personalization and Recommendation: Studies of user behavior, including longitudinal effects of personalized systems
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Radiotherapy continues to become more precise and data dense, with current treatment regimens generating high frequency imaging and dosimetry streams ideally suited for AI driven temporal modeling to characterize how normal tissues evolve with time. Each fraction in biologically guided radiotherapy(BGRT) treated non small cell lung cancer (NSCLC) patients records new metabolic, anatomical, and dose information. However, clinical decision making is largely informed by static, population based NTCP models which overlook the dynamic, unique biological trajectories encoded in sequential data. We developed COMPASS (Comprehensive Personalized Assessment System) for safe radiotherapy, functioning as a temporal digital twin architecture utilizing per fraction PET, CT, dosiomics, radiomics, and cumulative biologically equivalent dose (BED) kinetics to model normal tissue biology as a dynamic time series process. A GRU autoencoder was employed to learn organ specific latent trajectories, which were classified via logistic regression to predict eventual CTCAE grade 1 or higher toxicity. Eight NSCLC patients undergoing BGRT contributed to the 99 organ fraction observations covering 24 organ trajectories (spinal cord, heart, and esophagus). Despite the small cohort, intensive temporal phenotyping allowed for comprehensive analysis of individual dose response dynamics. Our findings revealed a viable AI driven early warning window, as increasing risk ratings occurred from several fractions before clinical toxicity. The dense BED driven representation revealed biologically relevant spatial dose texture characteristics that occur before toxicity and are averaged out with traditional volume based dosimetry. COMPASS establishes a proof of concept for AI enabled adaptive radiotherapy, where treatment is guided by a continually updated digital twin that tracks each patients evolving biological response.

Problem

• adaptive radiotherapy
• digital twin
• non-small cell lung cancer
• temporal modeling
• normal tissue toxicity

Innovation

• digital twin
• adaptive radiotherapy
• temporal modeling
• dosiomics
• GRU autoencoder